© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 76820
    Prev
    Next
    INDEX
    Explanations

    phrases indicating preferences or choices related to simplicity or moderation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    less, smaller quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.57
    
    -0.50
    
    -0.47
     ویکی‌پدیا
    -0.47
     Toler
    -0.47
     Zayed
    -0.47
    -------
    -0.45
     désolés
    -0.45
    IVEREF
    -0.44
    :✨
    -0.43
    POSITIVE LOGITS
     simpler
    0.37
    UnusedPrivate
    0.33
     smaller
    0.32
    aVar
    0.32
    sourceMap
    0.31
    entait
    0.31
    vite
    0.30
     kleinere
    0.29
    simp
    0.29
    لود
    0.29
    Activations Density 0.224%

    No Known Activations